GCF-Net: Gated Clip Fusion Network for Video Action Recognition.
Jenhao HsiaoJiawei ChenChiu Man HoPublished in: CoRR (2021)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- recognition of human actions
- recognizing human actions
- action detection
- video clips
- static images
- motion features
- bag of words
- human activities
- activity recognition
- space time interest points
- mid level
- spatio temporal interest points
- human detection
- action recognition in videos
- computer vision
- recognizing actions
- video sequences
- video streams
- body parts
- depth sensors
- motion history images
- video data
- human pose
- bag of features
- video shots
- view invariant
- action primitives
- key frames
- wireless sensor networks
- human activity recognition
- human object interactions
- event detection
- video frames